These are weights for a version of mistralai/Mistral-7B-Instruct-v0.1
finetuned for multimodal applications.
Modalities
- XCLIPVideoModality (use
<video>
in text and providevideos
, encoded as 10 tokens)
Usage
GitHub: https://github.com/sshh12/multi_token (includes training scripts and basic inference server)
Dataset
sshh12/xclip-videoinstruct-finetune (100010 examples)
{'videos': ['https://www.youtube.com/watch?v=k_ZXmr8pmrs'], 'messages': [{'content': 'What are the main activities that take place in the video?', 'role': 'user'}, {'content': 'The main activities that take place in the video are the preparation of camera equipment by a man, a group of men riding a helicopter, and a man sailing a boat through the water.', 'role': 'assistant'}]}
Training Device(s)
name, pci.bus_id, vbios_version
NVIDIA RTX A6000, 00000000:82:00.0, 94.02.5C.00.02
Model
MistralLMMForCausalLM.model =
PeftModelForCausalLM(
(base_model): LoraModel(
(model): MistralLMMForCausalLM(
(model): MistralLMMModel(
(embed_tokens): Embedding(32000, 4096)
(layers): ModuleList(
(0-31): 32 x MistralDecoderLayer(
(self_attn): MistralAttention(
(q_proj): lora.Linear(
(base_layer): Linear(in_features=4096, out_features=4096, bias=False)
(lora_dropout): ModuleDict(
(default): Dropout(p=0.05, inplace=False)
)
(lora_A): ModuleDict(
(default): Linear(in_features=4096, out_features=64, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=64, out_features=4096, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
)
(k_proj): lora.Linear(
(base_layer): Linear(in_features=4096, out_features=1024, bias=False)
(lora_dropout): ModuleDict(
(default): Dropout(p=0.05, inplace=False)
)
(lora_A): ModuleDict(
(default): Linear(in_features=4096, out_features=64, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=64, out_features=1024, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
)
(v_proj): lora.Linear(
(base_layer): Linear(in_features=4096, out_features=1024, bias=False)
(lora_dropout): ModuleDict(
(default): Dropout(p=0.05, inplace=False)
)
(lora_A): ModuleDict(
(default): Linear(in_features=4096, out_features=64, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=64, out_features=1024, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
)
(o_proj): lora.Linear(
(base_layer): Linear(in_features=4096, out_features=4096, bias=False)
(lora_dropout): ModuleDict(
(default): Dropout(p=0.05, inplace=False)
)
(lora_A): ModuleDict(
(default): Linear(in_features=4096, out_features=64, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=64, out_features=4096, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
)
(rotary_emb): MistralRotaryEmbedding()
)
(mlp): MistralMLP(
(gate_proj): lora.Linear(
(base_layer): Linear(in_features=4096, out_features=14336, bias=False)
(lora_dropout): ModuleDict(
(default): Dropout(p=0.05, inplace=False)
)
(lora_A): ModuleDict(
(default): Linear(in_features=4096, out_features=64, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=64, out_features=14336, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
)
(up_proj): lora.Linear(
(base_layer): Linear(in_features=4096, out_features=14336, bias=False)
(lora_dropout): ModuleDict(
(default): Dropout(p=0.05, inplace=False)
)
(lora_A): ModuleDict(
(default): Linear(in_features=4096, out_features=64, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=64, out_features=14336, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
)
(down_proj): lora.Linear(
(base_layer): Linear(in_features=14336, out_features=4096, bias=False)
(lora_dropout): ModuleDict(
(default): Dropout(p=0.05, inplace=False)
)
(lora_A): ModuleDict(
(default): Linear(in_features=14336, out_features=64, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=64, out_features=4096, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
)
(act_fn): SiLU()
)
(input_layernorm): MistralRMSNorm()
(post_attention_layernorm): MistralRMSNorm()
)
)
(norm): MistralRMSNorm()
(video_xclip_lmm_projector): _MLPVectorProjector(
(mlps): ModuleList(
(0-9): 10 x Sequential(
(0): Linear(in_features=512, out_features=4096, bias=True)
(1): GELU(approximate='none')
(2): Linear(in_features=4096, out_features=4096, bias=True)
)
)
)
)
(lm_head): Linear(in_features=4096, out_features=32000, bias=False)
)
)
)
Framework versions
- PEFT 0.7.1
- Downloads last month
- 2
Model tree for sshh12/Mistral-7B-LoRA-XCLIP
Base model
mistralai/Mistral-7B-v0.1
Finetuned
mistralai/Mistral-7B-Instruct-v0.1